Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    choose

    np_max-act · gemini-2.0-flash

    The neuron fires on the closing “Whichever… you choose” recommendation phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ersion
    -0.07
    strncmp
    -0.07
     reklam
    -0.07
     duyệt
    -0.06
     bred
    -0.06
     потреб
    -0.06
    	buttons
    -0.06
    Dep
    -0.06
     Gio
    -0.06
    óc
    -0.06
    POSITIVE LOGITS
     arousal
    0.07
     destructive
    0.06
     уд
    0.06
     accumulation
    0.06
     Myst
    0.06
    (matrix
    0.06
    ًا
    0.06
     dabei
    0.06
     Highly
    0.06
    χα
    0.06
    Act Density 0.010%

    No Known Activations